MULTI-SPEAKER TRACKING USING MULTIPLE DISTRIBUTED MICROPHONE ARRAYS. Axel Plinge and Gernot A. Fink
|
|
- Darlene Charlene Norman
- 5 years ago
- Views:
Transcription
1 14 IEEE International Conference on Acoustic, Speech and Signal Processing (ICASSP) MULTI-SPEAKER TRACKING USING MULTIPLE DISTRIBUTED MICROPHONE ARRAYS Axel Plinge and Gernot A. Fink Department of Computer Science, TU Dortmund University, Dortmund, Germany ABSTRACT Tracking multiple speakers with microphone arrays is one of the key tasks in smart environments. For good accuracy in reverberant environments, several arrays should be distributed in the room. The method presented is using distributed nodes with microphone arrays that compute local angular speech detections. In an integrating node, these are associated using the spectra and tracks for multiple concurrent speaker are computed. Euclidean coordinates are derived by triangulation, which is improved by a quality based weighting. The method is not only robust against reverberation, but also against transmission errors and jitter. Test with real recordings show that good precision for practical applications can be achieved. Index Terms sensor node, speaker tracking, machine hearing 1. INTRODUCTION A smart environment is defined by its capability of understanding of and interaction with human behavior by means of sensors, actuators and dedicated processing. The implementation of perceptual capabilities that make sense of the sensory data is the basis for this ability. Robust acoustic speaker tracking is required for many practical scenarios like online lectures, video conferencing or meetings [1 3]. It facilitates automated camera control and selection as well as speaker and context identification. Acoustic localization is often done by the SRP-PHAT or generalized cross-correlation approach [4]. The resulting spatial likelihood can be modeled as mixture of Gaussians (MoG) because reverberant speech is found to produce Gaussian distributed peaks over time [5]. In order to track speakers using a single microphone array, temporal integration can be realized with a maximum likelihood approach [6] or particle filtering [7,8]. Multiple microphone arrays can be used for robust localization in reverberant environments. Their relative and absolute positioning can be derived manually or automatically [9 11]. If the arrays themselves do not have to be strictly synchronized, the system is more robust and easy to realize, especially when using radio connections. This work was supported by the German Research Foundation (DFG) under contract number Fi 799/5-1. Fig. 1. Proposed system: Multiple distributed nodes localize speech using microphone arrays and transmit to an integration node that calculates speaker tracks in Euclidean space. The emerging research field of machine hearing tries to incorporate features of the human hearing process into computational processing [1]. One key influence is the study and modeling of the hearing process according to the Auditory Scene Analysis (ASA) theory [13]. Recently, several biologically inspired systems were shown to outperform technical approaches to localization [14 16]. A recent application of machine hearing for speaker tracking suggested the use of spectra as cues for associating concurrent estimates, inspired by the observation that human listeners integrate streams from both ears using common cues [17]. It has been successfully applied to recordings of two microphone arrays [18]. Here we extended this approach to the use of multiple distributes nodes. The proposed system is illustrated in Fig. 1. Multiple distributed nodes are equipped with microphone arrays. Each node calculates concurrent angular speaker detections and transmits the spatial and spectral estimates to an integrating unit. There, the spectral information is employed to solve the ambiguity problem for multiple simultaneous detections for multiple concurrent speakers. The angular estimates are used to integrate the localizations over time; Euclidean coordinates are calculated by triangulation. It is shown that the spectral cues allow to resolve the association ambiguity for multiple nodes. For triangulation, a precision oriented weighting is introduced that both allows the integration of an arbitrary number of nodes and improves the Euclidean localization over unweighted averaging. The system is able to handle transmission errors and is robust against drift and jitter. y x /14/$ IEEE 614
2 . NODE-BASED LOCALIZATION Each node is equipped with a circular microphone array. The machine hearing approach introduced in [14] is applied. The cochlear and mid-brain model uses B = 16 frequency bands. For time windows of L =.6 s with a time step of k L/4 a set D k of combined tuples x = (θ, s) with azimuth θ and spectrum s = (s,..., s B 1 ) T is extracted as set of speech detections. Sources Ψ i are estimated by calculating clusters Ψ i = (Θ i, σ i, t i ) with mean angle Θ i, deviation σ i, and spectrum t i from the detections in the current and adjacent time frames x D k 1 D k D k+1 using the EM-algorithm as described in [18]. The probability of x to originate from Ψ i is p(x Ψ i ) = p a (x Ψ i )p s (x Ψ i ) (1) where the angular probability density for a detection x is calculated using the angular distance d(α, β) = min{36 α β, α β } as σ p a (x Ψ i ) = p a (x Θ i, σ i ) = e.5d(θ,θi) i πσ and the spectral similarity of a detection x = (θ, s) to a model spectrum t is calculated as normalized scalar product s p s (x Ψ i ) = s, t i b = s bt i,b t i. (3) b s b b t i,b The number of sources can be estimated by observing the typical variance of speaker localizations for the given array geometry. If σ i > Γ split =, the source i is split into two sources with θ i,j = θ i ± σ i, when two estimates get closer than a threshold d(θ i, θ j ) < Γ join = 1, the sources Ψ i,j are merged. The EM loop is converging quickly in less than iterations, allowing for real-time calculation. After this step, there are clustered source estimates E (m) k = {Ψ i } for each time frame at each node m. The resulting sparse set of positions and spectra amounts to below 3 kbps of data which may be transmitted over a wireless connection. () 3. INTEGRATION AND TRACKING The problem of ambiguity of multiple concurrent localizations by multiple nodes is illustrated in Fig.. To associate the estimates from different nodes, their spectra are correlated using (3), and the pairs with the strongest correlation are computed. By thereafter combining all pairs with common angles, sets of angular estimates over all nodes are derived. The Euclidean position of the source can be derived by triangulation using these sets. By calculating the intersection of the lines originating at two nodes center positions c (m,n) with the cluster angles Θ (m,n) the D position z (m,n) ( Θ (m), Θ (n)) is derived. Given two angles α, β the quality of the localization by intersection may be expressed as q(α, β) = sin(α β) (4) to reflect the fact that an angular difference of 9 yields the highest precision and an angular difference near or 18 the worst. In order to calculate one point from multiple intersections, the weighted sum m,n z = q ( Θ (m), Θ (n)) z ( (m,n) Θ (m), Θ (n)) m,n q ( Θ (m), Θ (n)) (5) is used. The effect is illustrated in Fig. 3. A combined tracking state Ω j,k = (Ψ (m) j,k,..., Ψ(n) j,k, z j,k) T represents the states of the track with label j for time step k. The probability of a new detection Ψ,k+1 to belong to a track Ψ j given the cluster angles is calculated for each node as p a (Ψ,k+1 Ψ j,k ) = p a (Θ j,k Θ,k+1, (σ,k+1 +σ j,k )/) (6) and then multiplied p(ψ (m),k+1,..., Ψ(n),k+1 Ω j,k) = o ( ) p a Ψ (o),k+1 Ψ(o) j,k to compute the consensus. For each set of new estimates, the track with the highest likelihood above a threshold ɛ a is (7) Fig.. The problem of ambiguity of multiple concurrent estimates: Without additional information, all four intersections are possible source positions. Using the spectral similarity, the correct intersections (circles) are chosen and the others (squares) are discarded. Fig. 3. Incorporating angular intersection quality into the triangulation: Using all pairwise intersections (circles) equally, the center (square) is computed as localization. When weighting by intersection quality, the steeper angles get favored and a more precise localization is achieved (star). 615
3 εa[ ] T 6 [s] PoAP EM SRP-PHAT Fig. 4. Localization error for a single node for simulation of a single speaker. chosen from all tracks not older than a t T T L (e.g. 1 s). The time-to-live covers gaps caused by speech pauses or detection or transmission failure. If no such track exists, a new one is started. 4. EVALUATION The method was investigated using simulations and then evaluated on recordings in a real conference room. A localization is considered correct if the angles hit the target within an average head width of. m or the D coordinates are within a typical persons shoulder width of.5 m. The precision and recall are calculated in.6 s windows based on the correct localizations. These margins should be sufficient for most practical applications Simulation of a Single Node A single microphone array was simulated using the imagesource method [19] with a shoe-box model. A stationary single speaker at varying positions was simulated with 3 db SNR and T 6 times up. s. The proposed method was compared to the SRP-PHAT approach, Fig. 4 shows the angular RMS (root mean square) error ε a. The SRP-PHAT shows a higher localization error than the proposed method, especially in cases of strong reverberation. Both an analysis of variance and randomization tests showed the difference to be statistically significant (p <.1) for all T 6 s. 4.. Simulation of multiple nodes In order to test the method, a simulation of five nodes located on a table in the center of the room and a single speaker moving around it, speaking from 18 static locations, was done using the image-source method Localization The error and its deviation over the room position for tracking with all five nodes is listed in table 1. The weighting by the intersection quality q consistently improves the results. T 6 [s] ε a [ ] ε l [m] pr. [%] re. [%]..1±1. -.3±.19 94±17 9±18 q.15±.5 1± 98±5.5 4.± ±1.1 75±3 69±31 q.31±.13 97±9 9± ± ±.51 75±9 67±31 q.39±.43 9±4 73±8 Table 1. Tracking error using five nodes in simulation without (-) and with weighting (q) used in triangulation. εl[m] T 6 [s] Fig. 5. Tracking error for different node counts Node Count In order to investigate the influence of the node count and the effect of transmission failure, a fixed number of nodes were selected randomly for each time step. Figure 5 shows the RMS D localization error ε l for different counts and reverberation times. When only two nodes can be used, the accuracy is significantly worse because the triangulation is using only bad angles in some cases. The accuracy increases with the number of nodes Drift and Jitter Drift can be avoided by using the integration nodes clock as reference by exchanging information every frame in real time. Exact clock synchronization is not required when using DoA estimates rather than TDoAs [11]. Severe jitter of up to a time step (L/4 =.15 s) may be the result of different clocks at the nodes or the transmission to the integrating node. This was simulated by introducing random jitter to the nodes inputs signals at T 6 =.5 s. The tracking error increases slightly only for jitter approaching the length of a time window (.6s) as displayed in Fig. 6. This shows that jitter can be neglected and no compensation is necessary. εl[m] jitter [s] Fig. 6. Tracking error for different intra-array jitter. 616
4 #1 one static speaker # one moving speaker #3 two static speakers #4 three speakers precision recall RMS pr. recall RMS pr. recall RMS pr. recall RMS θ () 1% 96% 6.4 1% 99% 7. 1% 96% % 76% 6.3 θ (1) 1% 96% 4.8 1% 99% 7.6 1% 99% 6.5 1% 99% 5. θ () 1% 96% 5.7 1% 99% 4.6 7% 69% % 96% 3.3 x,y 99% 95%. m 93% 93%.34 m 88% 85%.33 m 99% 98%.19 m Table. Tracking performance on real recordings Recordings In order to test the real-world performance, recordings of multiple moving speakers were made in a highly reverberant m 3 conference room of a smart house installation at our university. Signals from three circular microphone arrays with 5 microphones in a 5 cm radius embedded in a table were recorded at 48 khz. Each array was captured by a separate sound card. Recordings of coherent white noise showed a jitter of µs between the sound cards. A reverberation time of 67 ± 89 ms over the microphone signals was calculated using a blind estimation algorithm []. The linearized ground truth annotations did not reflect slight head movement or speed and position variations Speaker Localization As a general test of localization quality for the intended applications, a single speaker took 15 position sitting at and standing around the table uttering a sentence at each one. As listed in table, the angular precision was around 5 and about 95% recall was achieved. The D tracking had an error around. m. Without application of the weighting q, the error was 1.4 m. In sequence #, the speaker was moving slowly in front of the table on a linear trajectory. The angular precision was around 7 and 99% recall was achieved. The D tracking had an error around.34 m (.54 m without q). θ () [ ] θ (1) [ ] θ () [ ] x [m] y [m] speaker 1 speaker speaker 3 track 1 track track t [s] Fig. 7. Tracking three concurrent speakers (sequence #4) Concurrent Speakers In sequence #3, speaker starts talking, a second one joins in so that they then both talk concurrently and then only the second one keeps talking. The association by the spectra produced no errors. As listed in table, the angular precision was between 5-1 for the nodes, the higher error may reflect the fact that one speaker was very far from the table. Despite this, the D tracking had an error around.33 m with 85% recall. Three speakers were talking around the table in sequence #4. Figure 7 shows the tracking result. The association by the spectra produced no errors. The angular precision was around 5 and about 96% recall was achieved. The D tracking had an error around.19 m (.8 m without q). 5. CONCLUSION A method for multi-speaker tracking using distributed nodes with microphone arrays was described. Its capability of accurately tracking static as well as moving speakers was shown with recordings of natural speakers in a reverberant environment. The correct association of the speakers was shown by the ability to handle two or three concurrent speakers. The weighted triangulation is shown to derive improved Euclidean coordinates. The robustness against drift and jitter as well as temporary transmission failure was shown in simulation. Two to five nodes were used, where three nodes already produce good precision for practical applications. The method is realtime capable with a delay of below one second. 617
5 6. REFERENCES [1] Iain McCowan, Daniel Gatica-Perez, Samy Bengio, Guillaume Lathoud, Mark Barnard, and Dong Zhang, Automatic analysis of multimodal group actions in meetings., IEEE transactions on pattern analysis and machine intelligence, vol. 7, no. 3, pp , Mar. 5. [] Fotios Talantzis, Aristodemos Pnevmatikakis, and Anthony G Constantinides, Audio-visual active speaker tracking in cluttered indoors environments., IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society, vol. 39, pp. 7 15, Feb. 9. [3] Damien Kelly, Anil Kokaram, and Frank Boland, Voxel-Based Viterbi Active Speaker Tracking (V- VAST) with Best View Selection for Video Lecture Post-Production, in IEEE Int. Conf. on Acoustics, Speech, and Signal Processing, Prague, Czech Republic, 11, pp [4] Youssef Oualil, Friedrich Faubel, and Dietrich Klakow, A Fast Cumulative Steered Response Power for Multiple Speaker Detection and Localization, in European Signal Processing Conference, Marrakech, Morocco, 13. [5] Maximo Cobos, Jose J. Lopez, and Sascha Spors, Analysis of Room Reverberation Effects in Source Localization using Small Microphone Arrays, in International Symposium on Communications, Control and Signal Processing, Mar. 1. [6] Nilesh Madhu and Rainer Martin, A Scalable Framework for Multiple Speaker Localization and Tracking, in Int. Workshop on Acoustic Echo and Noise Control, Seattle, Washington USA, 8. [7] Maurice F. Fallon and Simon J. Godsill, Acoustic Source Localization and Tracking of a Time-Varying Number of Speakers, IEEE Trans. on Audio, Speech, and Language Processing, vol., no. 4, pp , 1. [8] Axel Plinge, Daniel Hauschildt, Marius H. Hennecke, and Gernot A. Fink, Multiple Speaker Tracking using a Microphone Array by Combining Auditory Processing and a Gaussian Mixture Cardinalized Probability Hypothesis Density Filter, in IEEE Int. Conf. on Acoustics, Speech, and Signal Processing, Prague, Czech Republic, 11, pp [9] Marc Pollefeys and David Nister, Direct Computation of Sound and Microphone Locations from Time- Difference-of-Arrival Data, in IEEE Int. Conf. on Acoustics, Speech, and Signal Processing, Las Vegas, NV, 8, pp [1] Marco Crocco, Alessio Del Bue, Matteo Bustreo, and Vittorio Murino, A Closed Form Solution to the Microphone Position Self-Calibration Problem, in IEEE Int. Conf. on Acoustics, Speech, and Signal Processing, Kyoto, Japan, Mar. 1, pp [11] Florian Jacob, Joerg Schmalenstroeer, and Reinhold Haeb-Umbach, DOA-based Microphone Array Postion Self-Calibration using Circular Statistics, in IEEE Int. Conf. on Acoustics, Speech, and Signal Processing, Vancouver, Canada, 13. [1] Richard F. Lyon, Machine Hearing An Emerging Field, IEEE Signal Processing Magazine, Sept. 1. [13] DeLiang Wang and Guy J. Brown, Eds., Computational Auditory Scene Analysis: Principles, Algorithms, and Applications, IEEE Press, 6. [14] Axel Plinge, Marius H. Hennecke, and Gernot A. Fink, Robust Neuro-Fuzzy Speaker Localization Using a Circular Microphone Array, in Int. Workshop on Acoustic Echo and Noise Control, Tel Aviv, Israel, Aug. 1. [15] John Woodruff and DeLiang Wang, Sequential Organization of Speech in Reverberant Environments by Integrating Monaural Grouping and Binaural Localization, IEEE Trans. on Audio, Speech, and Language Processing, vol. 18, no. 7, pp , Sept. 1. [16] Tobias May, Steven van de Par, and Armin Kohlrausch, A Probabilistic Model for Robust Localization Based on a Binaural Auditory Front-End, IEEE Trans. on Audio, Speech, and Language Processing, vol. 19, 11. [17] Albert S. Bregman, Auditory Scene Analysis, MIT Press, 199. [18] Axel Plinge and Gernot A. Fink, Online Multi-Speaker Tracking Using Multiple Microphone Arrays Informed by Auditory Scene Analysis, in European Signal Processing Conference, Marrakesh, Morocco, Sept. 13. [19] Jont B. Allen and David A. Berkley, Image method for efficiently simulating small-room acoustics, Journal of the Acoustical Society of America, vol. 65, no. 4, pp , [] Heinrich W. Löllmann, Emre Yilmaz, Marco Jeub, and Peter Vary, An improved algorithm for blind reverberation time estimation, in Int. Workshop on Acoustic Echo and Noise Control, Tel Aviv, Israel, Aug
GEOMETRY CALIBRATION OF DISTRIBUTED MICROPHONE ARRAYS EXPLOITING AUDIO-VISUAL CORRESPONDENCES. Axel Plinge and Gernot A. Fink
GEOMETRY CALIBRATION OF DISTRIBUTED MICROPHONE ARRAYS EXPLOITING AUDIO-VISUAL CORRESPONDENCES Axel Plinge and Gernot A. Fink Department of Computer Science, TU Dortmund University, Dortmund, Germany ABSTRACT
More informationBag-of-Features Acoustic Event Detection for Sensor Networks
Bag-of-Features Acoustic Event Detection for Sensor Networks Julian Kürby, René Grzeszick, Axel Plinge, and Gernot A. Fink Pattern Recognition, Computer Science XII, TU Dortmund University September 3,
More informationOmnidirectional Sound Source Tracking Based on Sequential Updating Histogram
Proceedings of APSIPA Annual Summit and Conference 5 6-9 December 5 Omnidirectional Sound Source Tracking Based on Sequential Updating Histogram Yusuke SHIIKI and Kenji SUYAMA School of Engineering, Tokyo
More informationRecent Advances in Acoustic Signal Extraction and Dereverberation
Recent Advances in Acoustic Signal Extraction and Dereverberation Emanuël Habets Erlangen Colloquium 2016 Scenario Spatial Filtering Estimated Desired Signal Undesired sound components: Sensor noise Competing
More informationMultiple Sound Sources Localization Using Energetic Analysis Method
VOL.3, NO.4, DECEMBER 1 Multiple Sound Sources Localization Using Energetic Analysis Method Hasan Khaddour, Jiří Schimmel Department of Telecommunications FEEC, Brno University of Technology Purkyňova
More informationMonaural and Binaural Speech Separation
Monaural and Binaural Speech Separation DeLiang Wang Perception & Neurodynamics Lab The Ohio State University Outline of presentation Introduction CASA approach to sound separation Ideal binary mask as
More informationSimultaneous Recognition of Speech Commands by a Robot using a Small Microphone Array
2012 2nd International Conference on Computer Design and Engineering (ICCDE 2012) IPCSIT vol. 49 (2012) (2012) IACSIT Press, Singapore DOI: 10.7763/IPCSIT.2012.V49.14 Simultaneous Recognition of Speech
More information1856 IEEE TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING, VOL. 18, NO. 7, SEPTEMBER /$ IEEE
1856 IEEE TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING, VOL. 18, NO. 7, SEPTEMBER 2010 Sequential Organization of Speech in Reverberant Environments by Integrating Monaural Grouping and Binaural
More informationMicrophone Array Power Ratio for Speech Quality Assessment in Noisy Reverberant Environments 1
for Speech Quality Assessment in Noisy Reverberant Environments 1 Prof. Israel Cohen Department of Electrical Engineering Technion - Israel Institute of Technology Technion City, Haifa 3200003, Israel
More informationConvention Paper Presented at the 131st Convention 2011 October New York, USA
Audio Engineering Society Convention Paper Presented at the 131st Convention 211 October 2 23 New York, USA This paper was peer-reviewed as a complete manuscript for presentation at this Convention. Additional
More informationJoint Position-Pitch Decomposition for Multi-Speaker Tracking
Joint Position-Pitch Decomposition for Multi-Speaker Tracking SPSC Laboratory, TU Graz 1 Contents: 1. Microphone Arrays SPSC circular array Beamforming 2. Source Localization Direction of Arrival (DoA)
More informationThe psychoacoustics of reverberation
The psychoacoustics of reverberation Steven van de Par Steven.van.de.Par@uni-oldenburg.de July 19, 2016 Thanks to Julian Grosse and Andreas Häußler 2016 AES International Conference on Sound Field Control
More informationAcoustic Source Tracking in Reverberant Environment Using Regional Steered Response Power Measurement
Acoustic Source Tracing in Reverberant Environment Using Regional Steered Response Power Measurement Kai Wu and Andy W. H. Khong School of Electrical and Electronic Engineering, Nanyang Technological University,
More informationRobust Low-Resource Sound Localization in Correlated Noise
INTERSPEECH 2014 Robust Low-Resource Sound Localization in Correlated Noise Lorin Netsch, Jacek Stachurski Texas Instruments, Inc. netsch@ti.com, jacek@ti.com Abstract In this paper we address the problem
More informationA FAST CUMULATIVE STEERED RESPONSE POWER FOR MULTIPLE SPEAKER DETECTION AND LOCALIZATION. Youssef Oualil, Friedrich Faubel, Dietrich Klakow
A FAST CUMULATIVE STEERED RESPONSE POWER FOR MULTIPLE SPEAKER DETECTION AND LOCALIZATION Youssef Oualil, Friedrich Faubel, Dietrich Klaow Spoen Language Systems, Saarland University, Saarbrücen, Germany
More informationPassive Emitter Geolocation using Agent-based Data Fusion of AOA, TDOA and FDOA Measurements
Passive Emitter Geolocation using Agent-based Data Fusion of AOA, TDOA and FDOA Measurements Alex Mikhalev and Richard Ormondroyd Department of Aerospace Power and Sensors Cranfield University The Defence
More informationVOL. 3, NO.11 Nov, 2012 ISSN Journal of Emerging Trends in Computing and Information Sciences CIS Journal. All rights reserved.
Effect of Fading Correlation on the Performance of Spatial Multiplexed MIMO systems with circular antennas M. A. Mangoud Department of Electrical and Electronics Engineering, University of Bahrain P. O.
More informationA Weighted Least Squares Algorithm for Passive Localization in Multipath Scenarios
A Weighted Least Squares Algorithm for Passive Localization in Multipath Scenarios Noha El Gemayel, Holger Jäkel, Friedrich K. Jondral Karlsruhe Institute of Technology, Germany, {noha.gemayel,holger.jaekel,friedrich.jondral}@kit.edu
More informationMikko Myllymäki and Tuomas Virtanen
NON-STATIONARY NOISE MODEL COMPENSATION IN VOICE ACTIVITY DETECTION Mikko Myllymäki and Tuomas Virtanen Department of Signal Processing, Tampere University of Technology Korkeakoulunkatu 1, 3370, Tampere,
More informationLocalization of underwater moving sound source based on time delay estimation using hydrophone array
Journal of Physics: Conference Series PAPER OPEN ACCESS Localization of underwater moving sound source based on time delay estimation using hydrophone array To cite this article: S. A. Rahman et al 2016
More informationSpeaker Localization in Noisy Environments Using Steered Response Voice Power
112 IEEE Transactions on Consumer Electronics, Vol. 61, No. 1, February 2015 Speaker Localization in Noisy Environments Using Steered Response Voice Power Hyeontaek Lim, In-Chul Yoo, Youngkyu Cho, and
More informationImproving reverberant speech separation with binaural cues using temporal context and convolutional neural networks
Improving reverberant speech separation with binaural cues using temporal context and convolutional neural networks Alfredo Zermini, Qiuqiang Kong, Yong Xu, Mark D. Plumbley, Wenwu Wang Centre for Vision,
More informationA Hybrid TDOA/RSSD Geolocation System using the Unscented Kalman Filter
A Hybrid TDOA/RSSD Geolocation System using the Unscented Kalman Filter Noha El Gemayel, Holger Jäkel and Friedrich K. Jondral Communications Engineering Lab, Karlsruhe Institute of Technology (KIT, Germany
More informationPerformance of Combined Error Correction and Error Detection for very Short Block Length Codes
Performance of Combined Error Correction and Error Detection for very Short Block Length Codes Matthias Breuninger and Joachim Speidel Institute of Telecommunications, University of Stuttgart Pfaffenwaldring
More informationTime-of-arrival estimation for blind beamforming
Time-of-arrival estimation for blind beamforming Pasi Pertilä, pasi.pertila (at) tut.fi www.cs.tut.fi/~pertila/ Aki Tinakari, aki.tinakari (at) tut.fi Tampere University of Technology Tampere, Finland
More informationSpatialized teleconferencing: recording and 'Squeezed' rendering of multiple distributed sites
University of Wollongong Research Online Faculty of Informatics - Papers (Archive) Faculty of Engineering and Information Sciences 2008 Spatialized teleconferencing: recording and 'Squeezed' rendering
More informationDistance Estimation and Localization of Sound Sources in Reverberant Conditions using Deep Neural Networks
Distance Estimation and Localization of Sound Sources in Reverberant Conditions using Deep Neural Networks Mariam Yiwere 1 and Eun Joo Rhee 2 1 Department of Computer Engineering, Hanbat National University,
More informationROBUST SUPERDIRECTIVE BEAMFORMER WITH OPTIMAL REGULARIZATION
ROBUST SUPERDIRECTIVE BEAMFORMER WITH OPTIMAL REGULARIZATION Aviva Atkins, Yuval Ben-Hur, Israel Cohen Department of Electrical Engineering Technion - Israel Institute of Technology Technion City, Haifa
More informationSmart antenna for doa using music and esprit
IOSR Journal of Electronics and Communication Engineering (IOSRJECE) ISSN : 2278-2834 Volume 1, Issue 1 (May-June 2012), PP 12-17 Smart antenna for doa using music and esprit SURAYA MUBEEN 1, DR.A.M.PRASAD
More informationIMPROVED COCKTAIL-PARTY PROCESSING
IMPROVED COCKTAIL-PARTY PROCESSING Alexis Favrot, Markus Erne Scopein Research Aarau, Switzerland postmaster@scopein.ch Christof Faller Audiovisual Communications Laboratory, LCAV Swiss Institute of Technology
More informationarxiv: v1 [cs.sd] 4 Dec 2018
LOCALIZATION AND TRACKING OF AN ACOUSTIC SOURCE USING A DIAGONAL UNLOADING BEAMFORMING AND A KALMAN FILTER Daniele Salvati, Carlo Drioli, Gian Luca Foresti Department of Mathematics, Computer Science and
More informationAuditory System For a Mobile Robot
Auditory System For a Mobile Robot PhD Thesis Jean-Marc Valin Department of Electrical Engineering and Computer Engineering Université de Sherbrooke, Québec, Canada Jean-Marc.Valin@USherbrooke.ca Motivations
More informationEffects of Reverberation on Pitch, Onset/Offset, and Binaural Cues
Effects of Reverberation on Pitch, Onset/Offset, and Binaural Cues DeLiang Wang Perception & Neurodynamics Lab The Ohio State University Outline of presentation Introduction Human performance Reverberation
More informationMichael Brandstein Darren Ward (Eds.) Microphone Arrays. Signal Processing Techniques and Applications. With 149 Figures. Springer
Michael Brandstein Darren Ward (Eds.) Microphone Arrays Signal Processing Techniques and Applications With 149 Figures Springer Contents Part I. Speech Enhancement 1 Constant Directivity Beamforming Darren
More informationAiro Interantional Research Journal September, 2013 Volume II, ISSN:
Airo Interantional Research Journal September, 2013 Volume II, ISSN: 2320-3714 Name of author- Navin Kumar Research scholar Department of Electronics BR Ambedkar Bihar University Muzaffarpur ABSTRACT Direction
More informationSpeech Enhancement Using Beamforming Dr. G. Ramesh Babu 1, D. Lavanya 2, B. Yamuna 2, H. Divya 2, B. Shiva Kumar 2, B.
www.ijecs.in International Journal Of Engineering And Computer Science ISSN:2319-7242 Volume 4 Issue 4 April 2015, Page No. 11143-11147 Speech Enhancement Using Beamforming Dr. G. Ramesh Babu 1, D. Lavanya
More informationSelf Localization Using A Modulated Acoustic Chirp
Self Localization Using A Modulated Acoustic Chirp Brian P. Flanagan The MITRE Corporation, 7515 Colshire Dr., McLean, VA 2212, USA; bflan@mitre.org ABSTRACT This paper describes a robust self localization
More informationEnhancement of Speech Signal Based on Improved Minima Controlled Recursive Averaging and Independent Component Analysis
Enhancement of Speech Signal Based on Improved Minima Controlled Recursive Averaging and Independent Component Analysis Mohini Avatade & S.L. Sahare Electronics & Telecommunication Department, Cummins
More informationWhite Rose Research Online URL for this paper: Version: Accepted Version
This is a repository copy of Exploiting Deep Neural Networks and Head Movements for Robust Binaural Localisation of Multiple Sources in Reverberant Environments. White Rose Research Online URL for this
More informationCompressed Sensing for Multiple Access
Compressed Sensing for Multiple Access Xiaodai Dong Wireless Signal Processing & Networking Workshop: Emerging Wireless Technologies, Tohoku University, Sendai, Japan Oct. 28, 2013 Outline Background Existing
More informationPERFORMANCE COMPARISON BETWEEN STEREAUSIS AND INCOHERENT WIDEBAND MUSIC FOR LOCALIZATION OF GROUND VEHICLES ABSTRACT
Approved for public release; distribution is unlimited. PERFORMANCE COMPARISON BETWEEN STEREAUSIS AND INCOHERENT WIDEBAND MUSIC FOR LOCALIZATION OF GROUND VEHICLES September 1999 Tien Pham U.S. Army Research
More informationJoint recognition and direction-of-arrival estimation of simultaneous meetingroom acoustic events
INTERSPEECH 2013 Joint recognition and direction-of-arrival estimation of simultaneous meetingroom acoustic events Rupayan Chakraborty and Climent Nadeu TALP Research Centre, Department of Signal Theory
More informationHigh-speed Noise Cancellation with Microphone Array
Noise Cancellation a Posteriori Probability, Maximum Criteria Independent Component Analysis High-speed Noise Cancellation with Microphone Array We propose the use of a microphone array based on independent
More informationIMPROVEMENT OF SPEECH SOURCE LOCALIZATION IN NOISY ENVIRONMENT USING OVERCOMPLETE RATIONAL-DILATION WAVELET TRANSFORMS
1 International Conference on Cyberworlds IMPROVEMENT OF SPEECH SOURCE LOCALIZATION IN NOISY ENVIRONMENT USING OVERCOMPLETE RATIONAL-DILATION WAVELET TRANSFORMS Di Liu, Andy W. H. Khong School of Electrical
More informationAutomotive three-microphone voice activity detector and noise-canceller
Res. Lett. Inf. Math. Sci., 005, Vol. 7, pp 47-55 47 Available online at http://iims.massey.ac.nz/research/letters/ Automotive three-microphone voice activity detector and noise-canceller Z. QI and T.J.MOIR
More informationDigital Modulation Recognition Based on Feature, Spectrum and Phase Analysis and its Testing with Disturbed Signals
Digital Modulation Recognition Based on Feature, Spectrum and Phase Analysis and its Testing with Disturbed Signals A. KUBANKOVA AND D. KUBANEK Department of Telecommunications Brno University of Technology
More informationIndoor Localization based on Multipath Fingerprinting. Presented by: Evgeny Kupershtein Instructed by: Assoc. Prof. Israel Cohen and Dr.
Indoor Localization based on Multipath Fingerprinting Presented by: Evgeny Kupershtein Instructed by: Assoc. Prof. Israel Cohen and Dr. Mati Wax Research Background This research is based on the work that
More informationIndoor Location Detection
Indoor Location Detection Arezou Pourmir Abstract: This project is a classification problem and tries to distinguish some specific places from each other. We use the acoustic waves sent from the speaker
More informationA JOINT MODULATION IDENTIFICATION AND FREQUENCY OFFSET CORRECTION ALGORITHM FOR QAM SYSTEMS
A JOINT MODULATION IDENTIFICATION AND FREQUENCY OFFSET CORRECTION ALGORITHM FOR QAM SYSTEMS Evren Terzi, Hasan B. Celebi, and Huseyin Arslan Department of Electrical Engineering, University of South Florida
More informationRecurrent Timing Neural Networks for Joint F0-Localisation Estimation
Recurrent Timing Neural Networks for Joint F0-Localisation Estimation Stuart N. Wrigley and Guy J. Brown Department of Computer Science, University of Sheffield Regent Court, 211 Portobello Street, Sheffield
More informationCHAPTER 6 SIGNAL PROCESSING TECHNIQUES TO IMPROVE PRECISION OF SPECTRAL FIT ALGORITHM
CHAPTER 6 SIGNAL PROCESSING TECHNIQUES TO IMPROVE PRECISION OF SPECTRAL FIT ALGORITHM After developing the Spectral Fit algorithm, many different signal processing techniques were investigated with the
More informationImproved Detection by Peak Shape Recognition Using Artificial Neural Networks
Improved Detection by Peak Shape Recognition Using Artificial Neural Networks Stefan Wunsch, Johannes Fink, Friedrich K. Jondral Communications Engineering Lab, Karlsruhe Institute of Technology Stefan.Wunsch@student.kit.edu,
More informationMaster s Thesis Defense
Master s Thesis Defense Comparison of Noncoherent Detectors for SOQPSK and GMSK in Phase Noise Channels Afzal Syed August 17, 2007 Committee Dr. Erik Perrins (Chair) Dr. Glenn Prescott Dr. Daniel Deavours
More informationDetection of Compound Structures in Very High Spatial Resolution Images
Detection of Compound Structures in Very High Spatial Resolution Images Selim Aksoy Department of Computer Engineering Bilkent University Bilkent, 06800, Ankara, Turkey saksoy@cs.bilkent.edu.tr Joint work
More informationMicrophone Array Design and Beamforming
Microphone Array Design and Beamforming Heinrich Löllmann Multimedia Communications and Signal Processing heinrich.loellmann@fau.de with contributions from Vladi Tourbabin and Hendrik Barfuss EUSIPCO Tutorial
More informationSPEAKER CHANGE DETECTION AND SPEAKER DIARIZATION USING SPATIAL INFORMATION.
SPEAKER CHANGE DETECTION AND SPEAKER DIARIZATION USING SPATIAL INFORMATION Mathieu Hu 1, Dushyant Sharma, Simon Doclo 3, Mike Brookes 1, Patrick A. Naylor 1 1 Department of Electrical and Electronic Engineering,
More informationVariable Step-Size LMS Adaptive Filters for CDMA Multiuser Detection
FACTA UNIVERSITATIS (NIŠ) SER.: ELEC. ENERG. vol. 7, April 4, -3 Variable Step-Size LMS Adaptive Filters for CDMA Multiuser Detection Karen Egiazarian, Pauli Kuosmanen, and Radu Ciprian Bilcu Abstract:
More informationAudio data fuzzy fusion for source localization
International Neural Network Society 13-16 September, 2013, Halkidiki, Greece Audio data fuzzy fusion for source localization M. Malcangi Università degli Studi di Milano Department of Computer Science
More informationCo-Prime Sampling and Cross-Correlation Estimation
Twenty Fourth National Conference on Communications (NCC) Co-Prime Sampling and Estimation Usham V. Dias and Seshan Srirangarajan Department of Electrical Engineering Bharti School of Telecommunication
More informationBinaural Hearing. Reading: Yost Ch. 12
Binaural Hearing Reading: Yost Ch. 12 Binaural Advantages Sounds in our environment are usually complex, and occur either simultaneously or close together in time. Studies have shown that the ability to
More informationInterfacing with the Machine
Interfacing with the Machine Jay Desloge SENS Corporation Sumit Basu Microsoft Research They (We) Are Better Than We Think! Machine source separation, localization, and recognition are not as distant as
More informationSOUND SOURCE LOCATION METHOD
SOUND SOURCE LOCATION METHOD Michal Mandlik 1, Vladimír Brázda 2 Summary: This paper deals with received acoustic signals on microphone array. In this paper the localization system based on a speaker speech
More informationMULTIMODAL BLIND SOURCE SEPARATION WITH A CIRCULAR MICROPHONE ARRAY AND ROBUST BEAMFORMING
19th European Signal Processing Conference (EUSIPCO 211) Barcelona, Spain, August 29 - September 2, 211 MULTIMODAL BLIND SOURCE SEPARATION WITH A CIRCULAR MICROPHONE ARRAY AND ROBUST BEAMFORMING Syed Mohsen
More informationVoice Activity Detection
Voice Activity Detection Speech Processing Tom Bäckström Aalto University October 2015 Introduction Voice activity detection (VAD) (or speech activity detection, or speech detection) refers to a class
More informationError Analysis of a Low Cost TDoA Sensor Network
Error Analysis of a Low Cost TDoA Sensor Network Noha El Gemayel, Holger Jäkel and Friedrich K. Jondral Communications Engineering Lab, Karlsruhe Institute of Technology (KIT), Germany {noha.gemayel, holger.jaekel,
More informationChapter 2 Distributed Consensus Estimation of Wireless Sensor Networks
Chapter 2 Distributed Consensus Estimation of Wireless Sensor Networks Recently, consensus based distributed estimation has attracted considerable attention from various fields to estimate deterministic
More informationSound Processing Technologies for Realistic Sensations in Teleworking
Sound Processing Technologies for Realistic Sensations in Teleworking Takashi Yazu Makoto Morito In an office environment we usually acquire a large amount of information without any particular effort
More informationSound source localization and its use in multimedia applications
Notes for lecture/ Zack Settel, McGill University Sound source localization and its use in multimedia applications Introduction With the arrival of real-time binaural or "3D" digital audio processing,
More informationAuditory Localization
Auditory Localization CMPT 468: Sound Localization Tamara Smyth, tamaras@cs.sfu.ca School of Computing Science, Simon Fraser University November 15, 2013 Auditory locatlization is the human perception
More informationImproving Meetings with Microphone Array Algorithms. Ivan Tashev Microsoft Research
Improving Meetings with Microphone Array Algorithms Ivan Tashev Microsoft Research Why microphone arrays? They ensure better sound quality: less noises and reverberation Provide speaker position using
More informationWITH the advent of ubiquitous computing, a significant
IEEE TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING, VOL. 15, NO. 8, NOVEMBER 2007 2257 Speech Enhancement and Recognition in Meetings With an Audio Visual Sensor Array Hari Krishna Maganti, Student
More informationACOUSTIC SOURCE LOCALIZATION IN HOME ENVIRONMENTS - THE EFFECT OF MICROPHONE ARRAY GEOMETRY
28. Konferenz Elektronische Sprachsignalverarbeitung 2017, Saarbrücken ACOUSTIC SOURCE LOCALIZATION IN HOME ENVIRONMENTS - THE EFFECT OF MICROPHONE ARRAY GEOMETRY Timon Zietlow 1, Hussein Hussein 2 and
More informationStefan Launer, Lyon, January 2011 Phonak AG, Stäfa, CH
State of art and Challenges in Improving Speech Intelligibility in Hearing Impaired People Stefan Launer, Lyon, January 2011 Phonak AG, Stäfa, CH Content Phonak Stefan Launer, Speech in Noise Workshop,
More informationMerging Propagation Physics, Theory and Hardware in Wireless. Ada Poon
HKUST January 3, 2007 Merging Propagation Physics, Theory and Hardware in Wireless Ada Poon University of Illinois at Urbana-Champaign Outline Multiple-antenna (MIMO) channels Human body wireless channels
More informationSpatialization and Timbre for Effective Auditory Graphing
18 Proceedings o1't11e 8th WSEAS Int. Conf. on Acoustics & Music: Theory & Applications, Vancouver, Canada. June 19-21, 2007 Spatialization and Timbre for Effective Auditory Graphing HONG JUN SONG and
More informationAdaptive Beamforming Applied for Signals Estimated with MUSIC Algorithm
Buletinul Ştiinţific al Universităţii "Politehnica" din Timişoara Seria ELECTRONICĂ şi TELECOMUNICAŢII TRANSACTIONS on ELECTRONICS and COMMUNICATIONS Tom 57(71), Fascicola 2, 2012 Adaptive Beamforming
More informationNicholas Chong, Shanhung Wong, Sven Nordholm, Iain Murray
MULTIPLE SOUND SOURCE TRACKING AND IDENTIFICATION VIA DEGENERATE UNMIXING ESTIMATION TECHNIQUE AND CARDINALITY BALANCED MULTI-TARGET MULTI-BERNOULLI FILTER (DUET-CBMEMBER) WITH TRACK MANAGEMENT Nicholas
More informationChannel Modelling ETIN10. Directional channel models and Channel sounding
Channel Modelling ETIN10 Lecture no: 7 Directional channel models and Channel sounding Ghassan Dahman / Fredrik Tufvesson Department of Electrical and Information Technology Lund University, Sweden 2014-02-17
More informationIntegrated Vision and Sound Localization
Integrated Vision and Sound Localization Parham Aarabi Safwat Zaky Department of Electrical and Computer Engineering University of Toronto 10 Kings College Road, Toronto, Ontario, Canada, M5S 3G4 parham@stanford.edu
More informationA classification-based cocktail-party processor
A classification-based cocktail-party processor Nicoleta Roman, DeLiang Wang Department of Computer and Information Science and Center for Cognitive Science The Ohio State University Columbus, OH 43, USA
More informationAUDIO VISUAL TRACKING OF A SPEAKER BASED ON FFT AND KALMAN FILTER
AUDIO VISUAL TRACKING OF A SPEAKER BASED ON FFT AND KALMAN FILTER Muhammad Muzammel, Mohd Zuki Yusoff, Mohamad Naufal Mohamad Saad and Aamir Saeed Malik Centre for Intelligent Signal and Imaging Research,
More informationEvaluation of clipping-noise suppression of stationary-noisy speech based on spectral compensation
Evaluation of clipping-noise suppression of stationary-noisy speech based on spectral compensation Takahiro FUKUMORI ; Makoto HAYAKAWA ; Masato NAKAYAMA 2 ; Takanobu NISHIURA 2 ; Yoichi YAMASHITA 2 Graduate
More informationAbderrahim Benslimane, Professor of Computer Sciences Coordinator of the Faculty of Engineering Head of the Informatic Research Center (CRI)
Wireless Sensor Networks for Smart Environments: A Focus on the Localization Abderrahim Benslimane, Professor of Computer Sciences Coordinator of the Faculty of Engineering Head of the Informatic Research
More informationAdaptive Waveforms for Target Class Discrimination
Adaptive Waveforms for Target Class Discrimination Jun Hyeong Bae and Nathan A. Goodman Department of Electrical and Computer Engineering University of Arizona 3 E. Speedway Blvd, Tucson, Arizona 857 dolbit@email.arizona.edu;
More informationNonlinear postprocessing for blind speech separation
Nonlinear postprocessing for blind speech separation Dorothea Kolossa and Reinhold Orglmeister 1 TU Berlin, Berlin, Germany, D.Kolossa@ee.tu-berlin.de, WWW home page: http://ntife.ee.tu-berlin.de/personen/kolossa/home.html
More informationLCRT: A ToA Based Mobile Terminal Localization Algorithm in NLOS Environment
: A ToA Based Mobile Terminal Localization Algorithm in NLOS Environment Lei Jiao, Frank Y. Li Dept. of Information and Communication Technology University of Agder (UiA) N-4898 Grimstad, rway Email: {lei.jiao;
More informationEmanuël A. P. Habets, Jacob Benesty, and Patrick A. Naylor. Presented by Amir Kiperwas
Emanuël A. P. Habets, Jacob Benesty, and Patrick A. Naylor Presented by Amir Kiperwas 1 M-element microphone array One desired source One undesired source Ambient noise field Signals: Broadband Mutually
More informationSampling Rate Synchronisation in Acoustic Sensor Networks with a Pre-Trained Clock Skew Error Model
in Acoustic Sensor Networks with a Pre-Trained Clock Skew Error Model Joerg Schmalenstroeer, Reinhold Haeb-Umbach Department of Communications Engineering - University of Paderborn 12.09.2013 Computer
More informationTDE-ILD-HRTF-Based 2D Whole-Plane Sound Source Localization Using Only Two Microphones and Source Counting
TDE-ILD-HRTF-Based 2D Whole-Plane Sound Source Localization Using Only Two Microphones Source Counting Ali Pourmohammad, Member, IACSIT Seyed Mohammad Ahadi Abstract In outdoor cases, TDOA-based methods
More informationColor Constancy Using Standard Deviation of Color Channels
2010 International Conference on Pattern Recognition Color Constancy Using Standard Deviation of Color Channels Anustup Choudhury and Gérard Medioni Department of Computer Science University of Southern
More informationChannel Modelling ETI 085
Channel Modelling ETI 085 Lecture no: 7 Directional channel models Channel sounding Why directional channel models? The spatial domain can be used to increase the spectral efficiency i of the system Smart
More informationAnalysis and Improvements of Linear Multi-user user MIMO Precoding Techniques
1 Analysis and Improvements of Linear Multi-user user MIMO Precoding Techniques Bin Song and Martin Haardt Outline 2 Multi-user user MIMO System (main topic in phase I and phase II) critical problem Downlink
More informationAn Accurate and Efficient Analysis of a MBSFN Network
An Accurate and Efficient Analysis of a MBSFN Network Matthew C. Valenti West Virginia University Morgantown, WV May 9, 2014 An Accurate (shortinst) and Efficient Analysis of a MBSFN Network May 9, 2014
More informationDetection of Obscured Targets: Signal Processing
Detection of Obscured Targets: Signal Processing James McClellan and Waymond R. Scott, Jr. School of Electrical and Computer Engineering Georgia Institute of Technology Atlanta, GA 30332-0250 jim.mcclellan@ece.gatech.edu
More informationChannel Probability Ensemble Update for Multiplatform Radar Systems
Channel Probability Ensemble Update for Multiplatform Radar Systems Ric A. Romero, Christopher M. Kenyon, and Nathan A. Goodman Electrical and Computer Engineering University of Arizona Tucson, AZ, USA
More informationA MICROPHONE ARRAY INTERFACE FOR REAL-TIME INTERACTIVE MUSIC PERFORMANCE
A MICROPHONE ARRA INTERFACE FOR REAL-TIME INTERACTIVE MUSIC PERFORMANCE Daniele Salvati AVIRES lab Dep. of Mathematics and Computer Science, University of Udine, Italy daniele.salvati@uniud.it Sergio Canazza
More informationTime Synchronization and Distributed Modulation in Large-Scale Sensor Networks
Time Synchronization and Distributed Modulation in Large-Scale Sensor Networks Sergio D. Servetto School of Electrical and Computer Engineering Cornell University http://cn.ece.cornell.edu/ RPI Workshop
More informationAd hoc and Sensor Networks Chapter 9: Localization & positioning
Ad hoc and Sensor Networks Chapter 9: Localization & positioning Holger Karl Computer Networks Group Universität Paderborn Goals of this chapter Means for a node to determine its physical position (with
More informationPerformance Evaluation of Nonlinear Speech Enhancement Based on Virtual Increase of Channels in Reverberant Environments
Performance Evaluation of Nonlinear Speech Enhancement Based on Virtual Increase of Channels in Reverberant Environments Kouei Yamaoka, Shoji Makino, Nobutaka Ono, and Takeshi Yamada University of Tsukuba,
More informationSingle Channel Speaker Segregation using Sinusoidal Residual Modeling
NCC 2009, January 16-18, IIT Guwahati 294 Single Channel Speaker Segregation using Sinusoidal Residual Modeling Rajesh M Hegde and A. Srinivas Dept. of Electrical Engineering Indian Institute of Technology
More information